{"id":"W4416035479","doi":"10.18653/v1/2025.emnlp-main.1563","title":"Are Language Models Consequentialist or Deontological Moral Reasoners?","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Bundesministerium für Bildung und Forschung; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Natural language; Natural (archaeology); Empirical research; Consequentialism; On Language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007969113,0.0005692595,0.0007678873,0.0003200212,0.0006142519,0.001252263,0.002511102,0.0004455696,0.001903032],"category_scores_gemma":[0.000805968,0.0004588808,0.0002930896,0.001886538,0.0007920177,0.001441505,0.001219929,0.0006187659,0.0005805347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002956937,"about_ca_system_score_gemma":0.0008294838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00351863,"about_ca_topic_score_gemma":0.005652229,"domain_scores_codex":[0.9950961,0.0004920824,0.001009666,0.001504994,0.0006005099,0.001296586],"domain_scores_gemma":[0.9966094,0.000445748,0.0004050488,0.001717457,0.0004593295,0.0003629853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002586275,0.000429781,0.0004307335,0.000102799,0.0001069921,0.002419581,0.001750283,0.00197079,0.0005235514,0.9328797,0.01486763,0.04425956],"study_design_scores_gemma":[0.0004887381,0.0002264992,0.0004050815,0.0003680177,0.00009329138,0.0001009543,0.00873291,0.8890575,0.02502593,0.07189124,0.002674809,0.0009349991],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01929149,0.001967784,0.8357946,0.009730534,0.001871803,0.0007238587,0.0000202571,0.0005071349,0.1300926],"genre_scores_gemma":[0.925128,0.0001245102,0.01690757,0.005541692,0.0001233152,0.00005189352,0.000003725391,0.00001825952,0.05210105],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9058365,"threshold_uncertainty_score":0.9997863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1066088690734464,"score_gpt":0.3441283254344819,"score_spread":0.2375194563610355,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}